diff options
Diffstat (limited to 'arch/powerpc')
31 files changed, 354 insertions, 134 deletions
diff --git a/arch/powerpc/boot/dts/fsl/kmcoge4.dts b/arch/powerpc/boot/dts/fsl/kmcoge4.dts index ae70a24..e103c0f 100644 --- a/arch/powerpc/boot/dts/fsl/kmcoge4.dts +++ b/arch/powerpc/boot/dts/fsl/kmcoge4.dts @@ -83,6 +83,10 @@ }; }; + sdhc@114000 { + status = "disabled"; + }; + i2c@119000 { status = "disabled"; }; diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 2b90335..a2cc801 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -560,7 +560,7 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) * Atomically increments @v by 1, so long as @v is non-zero. * Returns non-zero if @v was non-zero, and zero otherwise. */ -static __inline__ long atomic64_inc_not_zero(atomic64_t *v) +static __inline__ int atomic64_inc_not_zero(atomic64_t *v) { long t1, t2; @@ -579,7 +579,7 @@ static __inline__ long atomic64_inc_not_zero(atomic64_t *v) : "r" (&v->counter) : "cc", "xer", "memory"); - return t1; + return t1 != 0; } #endif /* __powerpc64__ */ diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index ee46ffe..743ad7a 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -23,12 +23,13 @@ #define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE PAGE_SIZE -/* This is the location that an ET_DYN program is loaded if exec'ed. Typical - use of this is to invoke "./ld.so someprog" to test out a new version of - the loader. We need to make sure that it is out of the way of the program - that it will "exec", and that there is sufficient room for the brk. */ - -#define ELF_ET_DYN_BASE 0x20000000 +/* + * This is the base location for PIE (ET_DYN with INTERP) loads. On + * 64-bit, this is raised to 4GB to leave the entire 32-bit address + * space open for things that want to use the area for 32-bit pointers. + */ +#define ELF_ET_DYN_BASE (is_32bit_task() ? 0x000400000UL : \ + 0x100000000UL) #define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0) diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 0012f03..fe208b7 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -75,9 +75,27 @@ static inline void switch_mm_irqs_off(struct mm_struct *prev, struct task_struct *tsk) { /* Mark this context has been used on the new CPU */ - if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) + if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) { cpumask_set_cpu(smp_processor_id(), mm_cpumask(next)); + /* + * This full barrier orders the store to the cpumask above vs + * a subsequent operation which allows this CPU to begin loading + * translations for next. + * + * When using the radix MMU that operation is the load of the + * MMU context id, which is then moved to SPRN_PID. + * + * For the hash MMU it is either the first load from slb_cache + * in switch_slb(), and/or the store of paca->mm_ctx_id in + * copy_mm_to_paca(). + * + * On the read side the barrier is in pte_xchg(), which orders + * the store to the PTE vs the load of mm_cpumask. + */ + smp_mb(); + } + /* 32-bit keeps track of the current PGDIR in the thread struct */ #ifdef CONFIG_PPC32 tsk->thread.pgdir = next->pgd; diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h index 49c0a5a..68e087e 100644 --- a/arch/powerpc/include/asm/pgtable-be-types.h +++ b/arch/powerpc/include/asm/pgtable-be-types.h @@ -87,6 +87,7 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new) unsigned long *p = (unsigned long *)ptep; __be64 prev; + /* See comment in switch_mm_irqs_off() */ prev = (__force __be64)__cmpxchg_u64(p, (__force unsigned long)pte_raw(old), (__force unsigned long)pte_raw(new)); diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h index e7f4f3e..41e9d0a 100644 --- a/arch/powerpc/include/asm/pgtable-types.h +++ b/arch/powerpc/include/asm/pgtable-types.h @@ -62,6 +62,7 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new) { unsigned long *p = (unsigned long *)ptep; + /* See comment in switch_mm_irqs_off() */ return pte_val(old) == __cmpxchg_u64(p, pte_val(old), pte_val(new)); } #endif diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index e7d9eca..ceb168c 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1283,7 +1283,7 @@ static inline void msr_check_and_clear(unsigned long bits) " .llong 0\n" \ ".previous" \ : "=r" (rval) \ - : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL)); \ + : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \ rval;}) #else #define mftb() ({unsigned long rval; \ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 3297715..8b3b46b 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -44,22 +44,8 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); -static inline int early_cpu_to_node(int cpu) -{ - int nid; - - nid = numa_cpu_lookup_table[cpu]; - - /* - * Fall back to node 0 if nid is unset (it should be, except bugs). - * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)). - */ - return (nid < 0) ? 0 : nid; -} #else -static inline int early_cpu_to_node(int cpu) { return 0; } - static inline void dump_numa_cpu_topology(void) {} static inline int sysfs_add_device_to_node(struct device *dev, int nid) diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index b2da7c8..292458b 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -235,6 +235,28 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr) #define SWIZ_PTR(p) ((unsigned char __user *)((p) ^ swiz)) +#define __get_user_or_set_dar(_regs, _dest, _addr) \ + ({ \ + int rc = 0; \ + typeof(_addr) __addr = (_addr); \ + if (__get_user_inatomic(_dest, __addr)) { \ + _regs->dar = (unsigned long)__addr; \ + rc = -EFAULT; \ + } \ + rc; \ + }) + +#define __put_user_or_set_dar(_regs, _src, _addr) \ + ({ \ + int rc = 0; \ + typeof(_addr) __addr = (_addr); \ + if (__put_user_inatomic(_src, __addr)) { \ + _regs->dar = (unsigned long)__addr; \ + rc = -EFAULT; \ + } \ + rc; \ + }) + static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, unsigned int reg, unsigned int nb, unsigned int flags, unsigned int instr, @@ -263,9 +285,10 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, } else { unsigned long pc = regs->nip ^ (swiz & 4); - if (__get_user_inatomic(instr, - (unsigned int __user *)pc)) + if (__get_user_or_set_dar(regs, instr, + (unsigned int __user *)pc)) return -EFAULT; + if (swiz == 0 && (flags & SW)) instr = cpu_to_le32(instr); nb = (instr >> 11) & 0x1f; @@ -309,31 +332,31 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, ((nb0 + 3) / 4) * sizeof(unsigned long)); for (i = 0; i < nb; ++i, ++p) - if (__get_user_inatomic(REG_BYTE(rptr, i ^ bswiz), - SWIZ_PTR(p))) + if (__get_user_or_set_dar(regs, REG_BYTE(rptr, i ^ bswiz), + SWIZ_PTR(p))) return -EFAULT; if (nb0 > 0) { rptr = ®s->gpr[0]; addr += nb; for (i = 0; i < nb0; ++i, ++p) - if (__get_user_inatomic(REG_BYTE(rptr, - i ^ bswiz), - SWIZ_PTR(p))) + if (__get_user_or_set_dar(regs, + REG_BYTE(rptr, i ^ bswiz), + SWIZ_PTR(p))) return -EFAULT; } } else { for (i = 0; i < nb; ++i, ++p) - if (__put_user_inatomic(REG_BYTE(rptr, i ^ bswiz), - SWIZ_PTR(p))) + if (__put_user_or_set_dar(regs, REG_BYTE(rptr, i ^ bswiz), + SWIZ_PTR(p))) return -EFAULT; if (nb0 > 0) { rptr = ®s->gpr[0]; addr += nb; for (i = 0; i < nb0; ++i, ++p) - if (__put_user_inatomic(REG_BYTE(rptr, - i ^ bswiz), - SWIZ_PTR(p))) + if (__put_user_or_set_dar(regs, + REG_BYTE(rptr, i ^ bswiz), + SWIZ_PTR(p))) return -EFAULT; } } @@ -345,29 +368,32 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, * Only POWER6 has these instructions, and it does true little-endian, * so we don't need the address swizzling. */ -static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg, - unsigned int flags) +static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr, + unsigned int reg, unsigned int flags) { char *ptr0 = (char *) ¤t->thread.TS_FPR(reg); char *ptr1 = (char *) ¤t->thread.TS_FPR(reg+1); - int i, ret, sw = 0; + int i, sw = 0; if (reg & 1) return 0; /* invalid form: FRS/FRT must be even */ if (flags & SW) sw = 7; - ret = 0; + for (i = 0; i < 8; ++i) { if (!(flags & ST)) { - ret |= __get_user(ptr0[i^sw], addr + i); - ret |= __get_user(ptr1[i^sw], addr + i + 8); + if (__get_user_or_set_dar(regs, ptr0[i^sw], addr + i)) + return -EFAULT; + if (__get_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8)) + return -EFAULT; } else { - ret |= __put_user(ptr0[i^sw], addr + i); - ret |= __put_user(ptr1[i^sw], addr + i + 8); + if (__put_user_or_set_dar(regs, ptr0[i^sw], addr + i)) + return -EFAULT; + if (__put_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8)) + return -EFAULT; } } - if (ret) - return -EFAULT; + return 1; /* exception handled and fixed up */ } @@ -377,24 +403,27 @@ static int emulate_lq_stq(struct pt_regs *regs, unsigned char __user *addr, { char *ptr0 = (char *)®s->gpr[reg]; char *ptr1 = (char *)®s->gpr[reg+1]; - int i, ret, sw = 0; + int i, sw = 0; if (reg & 1) return 0; /* invalid form: GPR must be even */ if (flags & SW) sw = 7; - ret = 0; + for (i = 0; i < 8; ++i) { if (!(flags & ST)) { - ret |= __get_user(ptr0[i^sw], addr + i); - ret |= __get_user(ptr1[i^sw], addr + i + 8); + if (__get_user_or_set_dar(regs, ptr0[i^sw], addr + i)) + return -EFAULT; + if (__get_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8)) + return -EFAULT; } else { - ret |= __put_user(ptr0[i^sw], addr + i); - ret |= __put_user(ptr1[i^sw], addr + i + 8); + if (__put_user_or_set_dar(regs, ptr0[i^sw], addr + i)) + return -EFAULT; + if (__put_user_or_set_dar(regs, ptr1[i^sw], addr + i + 8)) + return -EFAULT; } } - if (ret) - return -EFAULT; + return 1; /* exception handled and fixed up */ } #endif /* CONFIG_PPC64 */ @@ -687,9 +716,14 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg, for (j = 0; j < length; j += elsize) { for (i = 0; i < elsize; ++i) { if (flags & ST) - ret |= __put_user(ptr[i^sw], addr + i); + ret = __put_user_or_set_dar(regs, ptr[i^sw], + addr + i); else - ret |= __get_user(ptr[i^sw], addr + i); + ret = __get_user_or_set_dar(regs, ptr[i^sw], + addr + i); + + if (ret) + return ret; } ptr += elsize; #ifdef __LITTLE_ENDIAN__ @@ -739,7 +773,7 @@ int fix_alignment(struct pt_regs *regs) unsigned int dsisr; unsigned char __user *addr; unsigned long p, swiz; - int ret, i; + int i; union data { u64 ll; double dd; @@ -936,7 +970,7 @@ int fix_alignment(struct pt_regs *regs) if (flags & F) { /* Special case for 16-byte FP loads and stores */ PPC_WARN_ALIGNMENT(fp_pair, regs); - return emulate_fp_pair(addr, reg, flags); + return emulate_fp_pair(regs, addr, reg, flags); } else { #ifdef CONFIG_PPC64 /* Special case for 16-byte loads and stores */ @@ -966,15 +1000,12 @@ int fix_alignment(struct pt_regs *regs) } data.ll = 0; - ret = 0; p = (unsigned long)addr; for (i = 0; i < nb; i++) - ret |= __get_user_inatomic(data.v[start + i], - SWIZ_PTR(p++)); - - if (unlikely(ret)) - return -EFAULT; + if (__get_user_or_set_dar(regs, data.v[start + i], + SWIZ_PTR(p++))) + return -EFAULT; } else if (flags & F) { data.ll = current->thread.TS_FPR(reg); @@ -1046,15 +1077,13 @@ int fix_alignment(struct pt_regs *regs) break; } - ret = 0; p = (unsigned long)addr; for (i = 0; i < nb; i++) - ret |= __put_user_inatomic(data.v[start + i], - SWIZ_PTR(p++)); + if (__put_user_or_set_dar(regs, data.v[start + i], + SWIZ_PTR(p++))) + return -EFAULT; - if (unlikely(ret)) - return -EFAULT; } else if (flags & F) current->thread.TS_FPR(reg) = data.ll; else diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index f257316..e5bfbf6 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -298,9 +298,17 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity) * * For pHyp, we have to enable IO for log retrieval. Otherwise, * 0xFF's is always returned from PCI config space. + * + * When the @severity is EEH_LOG_PERM, the PE is going to be + * removed. Prior to that, the drivers for devices included in + * the PE will be closed. The drivers rely on working IO path + * to bring the devices to quiet state. Otherwise, PCI traffic + * from those devices after they are removed is like to cause + * another unexpected EEH error. */ if (!(pe->type & EEH_PE_PHB)) { - if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG)) + if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG) || + severity == EEH_LOG_PERM) eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); /* diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 767ef6d..caa6596 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -1235,10 +1235,14 @@ _GLOBAL(ftrace_caller) stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save all gprs to pt_regs */ - SAVE_8GPRS(0,r1) - SAVE_8GPRS(8,r1) - SAVE_8GPRS(16,r1) - SAVE_8GPRS(24,r1) + SAVE_GPR(0, r1) + SAVE_10GPRS(2, r1) + SAVE_10GPRS(12, r1) + SAVE_10GPRS(22, r1) + + /* Save previous stack pointer (r1) */ + addi r8, r1, SWITCH_FRAME_SIZE + std r8, GPR1(r1) /* Load special regs for save below */ mfmsr r8 @@ -1292,10 +1296,10 @@ ftrace_call: #endif /* Restore gprs */ - REST_8GPRS(0,r1) - REST_8GPRS(8,r1) - REST_8GPRS(16,r1) - REST_8GPRS(24,r1) + REST_GPR(0,r1) + REST_10GPRS(2,r1) + REST_10GPRS(12,r1) + REST_10GPRS(22,r1) /* Restore callee's TOC */ ld r2, 24(r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 2e2fc1e..fd68e19 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -764,7 +764,29 @@ EXC_REAL(program_check, 0x700, 0x800) EXC_VIRT(program_check, 0x4700, 0x4800, 0x700) TRAMP_KVM(PACA_EXGEN, 0x700) EXC_COMMON_BEGIN(program_check_common) - EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) + /* + * It's possible to receive a TM Bad Thing type program check with + * userspace register values (in particular r1), but with SRR1 reporting + * that we came from the kernel. Normally that would confuse the bad + * stack logic, and we would report a bad kernel stack pointer. Instead + * we switch to the emergency stack if we're taking a TM Bad Thing from + * the kernel. + */ + li r10,MSR_PR /* Build a mask of MSR_PR .. */ + oris r10,r10,0x200000@h /* .. and SRR1_PROGTM */ + and r10,r10,r12 /* Mask SRR1 with that. */ + srdi r10,r10,8 /* Shift it so we can compare */ + cmpldi r10,(0x200000 >> 8) /* .. with an immediate. */ + bne 1f /* If != go to normal path. */ + + /* SRR1 had PR=0 and SRR1_PROGTM=1, so use the emergency stack */ + andi. r10,r12,MSR_PR; /* Set CR0 correctly for label */ + /* 3 in EXCEPTION_PROLOG_COMMON */ + mr r10,r1 /* Save r1 */ + ld r1,PACAEMERGSP(r13) /* Use emergency stack */ + subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + b 3f /* Jump into the macro !! */ +1: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 3c05c31..028a22b 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -146,6 +146,19 @@ notrace unsigned int __check_irq_replay(void) /* Clear bit 0 which we wouldn't clear otherwise */ local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; + if (happened & PACA_IRQ_HARD_DIS) { + /* + * We may have missed a decrementer interrupt if hard disabled. + * Check the decrementer register in case we had a rollover + * while hard disabled. + */ + if (!(happened & PACA_IRQ_DEC)) { + if (decrementer_check_overflow()) { + local_paca->irq_happened |= PACA_IRQ_DEC; + happened |= PACA_IRQ_DEC; + } + } + } /* * Force the delivery of pending soft-disabled interrupts on PS3. @@ -171,7 +184,7 @@ notrace unsigned int __check_irq_replay(void) * in case we also had a rollover while hard disabled */ local_paca->irq_happened &= ~PACA_IRQ_DEC; - if ((happened & PACA_IRQ_DEC) || decrementer_check_overflow()) + if (happened & PACA_IRQ_DEC) return 0x900; /* Finally check if an external interrupt happened */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index b249c2f..1c141d5 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -359,7 +359,8 @@ void enable_kernel_vsx(void) cpumsr = msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); - if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) { + if (current->thread.regs && + (current->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP))) { check_if_tm_restore_required(current); /* * If a thread has already been reclaimed then the @@ -383,7 +384,7 @@ void flush_vsx_to_thread(struct task_struct *tsk) { if (tsk->thread.regs) { preempt_disable(); - if (tsk->thread.regs->msr & MSR_VSX) { + if (tsk->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP)) { BUG_ON(tsk != current); giveup_vsx(tsk); } diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 5c8f12f..d973708 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -127,12 +127,19 @@ static void flush_tmregs_to_thread(struct task_struct *tsk) * If task is not current, it will have been flushed already to * it's thread_struct during __switch_to(). * - * A reclaim flushes ALL the state. + * A reclaim flushes ALL the state or if not in TM save TM SPRs + * in the appropriate thread structures from live. */ - if (tsk == current && MSR_TM_SUSPENDED(mfmsr())) - tm_reclaim_current(TM_CAUSE_SIGNAL); + if ((!cpu_has_feature(CPU_FTR_TM)) || (tsk != current)) + return; + if (MSR_TM_SUSPENDED(mfmsr())) { + tm_reclaim_current(TM_CAUSE_SIGNAL); + } else { + tm_enable(); + tm_save_sprs(&(tsk->thread)); + } } #else static inline void flush_tmregs_to_thread(struct task_struct *tsk) { } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index ada71be..a12be60 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -595,7 +595,7 @@ void __init emergency_stack_init(void) static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) { - return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align, + return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align, __pa(MAX_DMA_ADDRESS)); } @@ -606,7 +606,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size) static int pcpu_cpu_distance(unsigned int from, unsigned int to) { - if (early_cpu_to_node(from) == early_cpu_to_node(to)) + if (cpu_to_node(from) == cpu_to_node(to)) return LOCAL_DISTANCE; else return REMOTE_DISTANCE; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 96698fd..04e9225 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -452,9 +452,20 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, if (MSR_TM_RESV(msr)) return -EINVAL; - /* pull in MSR TM from user context */ + /* pull in MSR TS bits from user context */ regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); + /* + * Ensure that TM is enabled in regs->msr before we leave the signal + * handler. It could be the case that (a) user disabled the TM bit + * through the manipulation of the MSR bits in uc_mcontext or (b) the + * TM bit was disabled because a sufficient number of context switches + * happened whilst in the signal handler and load_tm overflowed, + * disabling the TM bit. In either case we can end up with an illegal + * TM state leading to a TM Bad Thing when we return to userspace. + */ + regs->msr |= MSR_TM; + /* pull in MSR LE from user context */ regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index bc3f7d0..f1d7e99 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -407,6 +407,7 @@ void arch_vtime_task_switch(struct task_struct *prev) struct cpu_accounting_data *acct = get_accounting(current); acct->starttime = get_accounting(prev)->starttime; + acct->startspurr = get_accounting(prev)->startspurr; acct->system_time = 0; acct->user_time = 0; } diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index c379ff5..da2a7ec 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -129,8 +129,11 @@ static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma) static int kvm_spapr_tce_release(struct inode *inode, struct file *filp) { struct kvmppc_spapr_tce_table *stt = filp->private_data; + struct kvm *kvm = stt->kvm; + mutex_lock(&kvm->lock); list_del_rcu(&stt->list); + mutex_unlock(&kvm->lock); kvm_put_kvm(stt->kvm); @@ -150,6 +153,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, struct kvm_create_spapr_tce_64 *args) { struct kvmppc_spapr_tce_table *stt = NULL; + struct kvmppc_spapr_tce_table *siter; unsigned long npages, size; int ret = -ENOMEM; int i; @@ -157,24 +161,16 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, if (!args->size) return -EINVAL; - /* Check this LIOBN hasn't been previously allocated */ - list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { - if (stt->liobn == args->liobn) - return -EBUSY; - } - size = args->size; npages = kvmppc_tce_pages(size); ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true); - if (ret) { - stt = NULL; - goto fail; - } + if (ret) + return ret; stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *), GFP_KERNEL); if (!stt) - goto fail; + goto fail_acct; stt->liobn = args->liobn; stt->page_shift = args->page_shift; @@ -188,24 +184,39 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, goto fail; } - kvm_get_kvm(kvm); - mutex_lock(&kvm->lock); - list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); + + /* Check this LIOBN hasn't been previously allocated */ + ret = 0; + list_for_each_entry(siter, &kvm->arch.spapr_tce_tables, list) { + if (siter->liobn == args->liobn) { + ret = -EBUSY; + break; + } + } + + if (!ret) + ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, + stt, O_RDWR | O_CLOEXEC); + + if (ret >= 0) { + list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); + kvm_get_kvm(kvm); + } mutex_unlock(&kvm->lock); - return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, - stt, O_RDWR | O_CLOEXEC); + if (ret >= 0) + return ret; -fail: - if (stt) { - for (i = 0; i < npages; i++) - if (stt->pages[i]) - __free_page(stt->pages[i]); + fail: + for (i = 0; i < npages; i++) + if (stt->pages[i]) + __free_page(stt->pages[i]); - kfree(stt); - } + kfree(stt); + fail_acct: + kvmppc_account_memlimit(kvmppc_stt_pages(npages), false); return ret; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 5c02984..218cba2 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2808,6 +2808,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) int r; int srcu_idx; unsigned long ebb_regs[3] = {}; /* shut up GCC */ + unsigned long user_tar = 0; + unsigned int user_vrsave; if (!vcpu->arch.sane) { run->exit_reason = KVM_EXIT_INTERNAL_ERROR; @@ -2828,6 +2830,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) run->fail_entry.hardware_entry_failure_reason = 0; return -EINVAL; } + /* Enable TM so we can read the TM SPRs */ + mtmsr(mfmsr() | MSR_TM); current->thread.tm_tfhar = mfspr(SPRN_TFHAR); current->thread.tm_tfiar = mfspr(SPRN_TFIAR); current->thread.tm_texasr = mfspr(SPRN_TEXASR); @@ -2856,12 +2860,14 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) flush_all_to_thread(current); - /* Save userspace EBB register values */ + /* Save userspace EBB and other register values */ if (cpu_has_feature(CPU_FTR_ARCH_207S)) { ebb_regs[0] = mfspr(SPRN_EBBHR); ebb_regs[1] = mfspr(SPRN_EBBRR); ebb_regs[2] = mfspr(SPRN_BESCR); + user_tar = mfspr(SPRN_TAR); } + user_vrsave = mfspr(SPRN_VRSAVE); vcpu->arch.wqp = &vcpu->arch.vcore->wq; vcpu->arch.pgdir = current->mm->pgd; @@ -2885,12 +2891,15 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) r = kvmppc_xics_rm_complete(vcpu, 0); } while (is_kvmppc_resume_guest(r)); - /* Restore userspace EBB register values */ + /* Restore userspace EBB and other register values */ if (cpu_has_feature(CPU_FTR_ARCH_207S)) { mtspr(SPRN_EBBHR, ebb_regs[0]); mtspr(SPRN_EBBRR, ebb_regs[1]); mtspr(SPRN_BESCR, ebb_regs[2]); + mtspr(SPRN_TAR, user_tar); + mtspr(SPRN_FSCR, current->thread.fscr); } + mtspr(SPRN_VRSAVE, user_vrsave); out: vcpu->arch.state = KVMPPC_VCPU_NOTREADY; diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index a0ea63a..a8e3498 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -376,6 +376,7 @@ static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, */ if (reject && reject != XICS_IPI) { arch_spin_unlock(&ics->lock); + icp->n_reject++; new_irq = reject; goto again; } @@ -707,10 +708,8 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) state = &ics->irq_state[src]; /* Still asserted, resend it */ - if (state->asserted) { - icp->n_reject++; + if (state->asserted) icp_rm_deliver_irq(xics, icp, irq); - } if (!hlist_empty(&vcpu->kvm->irq_ack_notifier_list)) { icp->rm_action |= XICS_RM_NOTIFY_EOI; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 6f81adb..0447a22 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -37,6 +37,13 @@ #define NAPPING_CEDE 1 #define NAPPING_NOVCPU 2 +/* Stack frame offsets for kvmppc_hv_entry */ +#define SFS 112 +#define STACK_SLOT_TRAP (SFS-4) +#define STACK_SLOT_CIABR (SFS-16) +#define STACK_SLOT_DAWR (SFS-24) +#define STACK_SLOT_DAWRX (SFS-32) + /* * Call kvmppc_hv_entry in real mode. * Must be called with interrupts hard-disabled. @@ -289,10 +296,10 @@ kvm_novcpu_exit: bl kvmhv_accumulate_time #endif 13: mr r3, r12 - stw r12, 112-4(r1) + stw r12, STACK_SLOT_TRAP(r1) bl kvmhv_commence_exit nop - lwz r12, 112-4(r1) + lwz r12, STACK_SLOT_TRAP(r1) b kvmhv_switch_to_host /* @@ -537,7 +544,7 @@ kvmppc_hv_entry: */ mflr r0 std r0, PPC_LR_STKOFF(r1) - stdu r1, -112(r1) + stdu r1, -SFS(r1) /* Save R1 in the PACA */ std r1, HSTATE_HOST_R1(r13) @@ -698,6 +705,16 @@ kvmppc_got_guest: mtspr SPRN_PURR,r7 mtspr SPRN_SPURR,r8 + /* Save host values of some registers */ +BEGIN_FTR_SECTION + mfspr r5, SPRN_CIABR + mfspr r6, SPRN_DAWR + mfspr r7, SPRN_DAWRX + std r5, STACK_SLOT_CIABR(r1) + std r6, STACK_SLOT_DAWR(r1) + std r7, STACK_SLOT_DAWRX(r1) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + BEGIN_FTR_SECTION /* Set partition DABR */ /* Do this before re-enabling PMU to avoid P7 DABR corruption bug */ @@ -1361,8 +1378,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) */ li r0, 0 mtspr SPRN_IAMR, r0 - mtspr SPRN_CIABR, r0 - mtspr SPRN_DAWRX, r0 + mtspr SPRN_PSPB, r0 mtspr SPRN_TCSCR, r0 mtspr SPRN_WORT, r0 /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ @@ -1378,6 +1394,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) std r6,VCPU_UAMOR(r9) li r6,0 mtspr SPRN_AMR,r6 + mtspr SPRN_UAMOR, r6 /* Switch DSCR back to host value */ mfspr r8, SPRN_DSCR @@ -1519,6 +1536,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) slbia ptesync + /* Restore host values of some registers */ +BEGIN_FTR_SECTION + ld r5, STACK_SLOT_CIABR(r1) + ld r6, STACK_SLOT_DAWR(r1) + ld r7, STACK_SLOT_DAWRX(r1) + mtspr SPRN_CIABR, r5 + mtspr SPRN_DAWR, r6 + mtspr SPRN_DAWRX, r7 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + /* * POWER7/POWER8 guest -> host partition switch code. * We don't have to lock against tlbies but we do @@ -1652,8 +1679,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) - ld r0, 112+PPC_LR_STKOFF(r1) - addi r1, r1, 112 + ld r0, SFS+PPC_LR_STKOFF(r1) + addi r1, r1, SFS mtlr r0 blr diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 70963c8..fc0df0f 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -601,8 +601,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; #endif case KVM_CAP_PPC_HTM: - r = cpu_has_feature(CPU_FTR_TM_COMP) && - is_kvmppc_hv_enabled(kvm); + r = cpu_has_feature(CPU_FTR_TM_COMP) && hv_enabled; break; default: r = 0; diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 6ca3b90..776c1a1 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -687,8 +687,10 @@ int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs, case 19: switch ((instr >> 1) & 0x3ff) { case 0: /* mcrf */ - rd = (instr >> 21) & 0x1c; - ra = (instr >> 16) & 0x1c; + rd = 7 - ((instr >> 23) & 0x7); + ra = 7 - ((instr >> 18) & 0x7); + rd *= 4; + ra *= 4; val = (regs->ccr >> ra) & 0xf; regs->ccr = (regs->ccr & ~(0xfUL << rd)) | (val << rd); goto instr_done; @@ -968,6 +970,19 @@ int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs, #endif case 19: /* mfcr */ + if ((instr >> 20) & 1) { + imm = 0xf0000000UL; + for (sh = 0; sh < 8; ++sh) { + if (instr & (0x80000 >> sh)) { + regs->gpr[rd] = regs->ccr & imm; + break; + } + imm >>= 4; + } + + goto instr_done; + } + regs->gpr[rd] = regs->ccr; regs->gpr[rd] &= 0xffffffffUL; goto instr_done; diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index d5ce34d..1e28747 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -42,6 +42,8 @@ #include <linux/memblock.h> #include <linux/hugetlb.h> #include <linux/slab.h> +#include <linux/of_fdt.h> +#include <linux/libfdt.h> #include <asm/pgalloc.h> #include <asm/page.h> @@ -421,6 +423,28 @@ static int __init parse_disable_radix(char *p) } early_param("disable_radix", parse_disable_radix); +/* + * If we're running under a hypervisor, we currently can't do radix + * since we don't have the code to do the H_REGISTER_PROC_TBL hcall. + * We tell that we're running under a hypervisor by looking for the + * /chosen/ibm,architecture-vec-5 property. + */ +static void early_check_vec5(void) +{ + unsigned long root, chosen; + int size; + const u8 *vec5; + + root = of_get_flat_dt_root(); + chosen = of_get_flat_dt_subnode_by_name(root, "chosen"); + if (chosen == -FDT_ERR_NOTFOUND) + return; + vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size); + if (!vec5) + return; + cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; +} + void __init mmu_early_init_devtree(void) { /* Disable radix mode based on kernel command line. */ @@ -428,6 +452,15 @@ void __init mmu_early_init_devtree(void) if (disable_radix || !(mfmsr() & MSR_HV)) cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; + /* + * Check /chosen/ibm,architecture-vec-5 if running as a guest. + * When running bare-metal, we can use radix if we like + * even though the ibm,architecture-vec-5 property created by + * skiboot doesn't have the necessary bits set. + */ + if (early_radix_enabled() && !(mfmsr() & MSR_HV)) + early_check_vec5(); + if (early_radix_enabled()) radix__early_init_devtree(); else diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 73bf6e1..a006f82 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -167,9 +167,15 @@ void destroy_context(struct mm_struct *mm) mm->context.cop_lockp = NULL; #endif /* CONFIG_PPC_ICSWX */ - if (radix_enabled()) - process_tb[mm->context.id].prtb1 = 0; - else + if (radix_enabled()) { + /* + * Radix doesn't have a valid bit in the process table + * entries. However we know that at least P9 implementation + * will avoid caching an entry with an invalid RTS field, + * and 0 is invalid. So this will do. + */ + process_tb[mm->context.id].prtb0 = 0; + } else subpage_prot_free(mm); destroy_pagetable_page(mm); __destroy_context(mm->context.id); diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h index 4d0a4e5..8e6dd17 100644 --- a/arch/powerpc/perf/isa207-common.h +++ b/arch/powerpc/perf/isa207-common.h @@ -201,6 +201,10 @@ CNST_PMC_VAL(1) | CNST_PMC_VAL(2) | CNST_PMC_VAL(3) | \ CNST_PMC_VAL(4) | CNST_PMC_VAL(5) | CNST_PMC_VAL(6) | CNST_NC_VAL +/* + * Lets restrict use of PMC5 for instruction counting. + */ +#define P9_DD1_TEST_ADDER (ISA207_TEST_ADDER | CNST_PMC_VAL(5)) /* Bits in MMCR1 for PowerISA v2.07 */ #define MMCR1_UNIT_SHIFT(pmc) (60 - (4 * ((pmc) - 1))) diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 8e9a819..9abcd8f 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -295,7 +295,7 @@ static struct power_pmu power9_pmu = { .name = "POWER9", .n_counter = MAX_PMU_COUNTERS, .add_fields = ISA207_ADD_FIELDS, - .test_adder = ISA207_TEST_ADDER, + .test_adder = P9_DD1_TEST_ADDER, .compute_mmcr = isa207_compute_mmcr, .config_bhrb = power9_config_bhrb, .bhrb_filter_map = power9_bhrb_filter_map, diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index f2c98f6..a7bb872 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -279,7 +279,7 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot, int ssize, unsigned long inv_flags) { unsigned long lpar_rc; - unsigned long flags = (newpp & 7) | H_AVPN; + unsigned long flags; unsigned long want_v; want_v = hpte_encode_avpn(vpn, psize, ssize); @@ -287,6 +287,11 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot, pr_devel(" update: avpnv=%016lx, hash=%016lx, f=%lx, psize: %d ...", want_v, slot, flags, psize); + flags = (newpp & 7) | H_AVPN; + if (mmu_has_feature(MMU_FTR_KERNEL_RO)) + /* Move pp0 into bit 8 (IBM 55) */ + flags |= (newpp & HPTE_R_PP0) >> 55; + lpar_rc = plpar_pte_protect(flags, slot, want_v); if (lpar_rc == H_NOT_FOUND) { @@ -358,6 +363,10 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp, BUG_ON(slot == -1); flags = newpp & 7; + if (mmu_has_feature(MMU_FTR_KERNEL_RO)) + /* Move pp0 into bit 8 (IBM 55) */ + flags |= (newpp & HPTE_R_PP0) >> 55; + lpar_rc = plpar_pte_protect(flags, slot, 0); BUG_ON(lpar_rc != H_SUCCESS); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index a560a98..6a5e746 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -225,8 +225,10 @@ static int add_dt_node(__be32 parent_phandle, __be32 drc_index) return -ENOENT; dn = dlpar_configure_connector(drc_index, parent_dn); - if (!dn) + if (!dn) { + of_node_put(parent_dn); return -ENOENT; + } rc = dlpar_attach_node(dn); if (rc) diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index cc66c49..666ad06 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -82,7 +82,6 @@ static int pSeries_reconfig_remove_node(struct device_node *np) of_detach_node(np); of_node_put(parent); - of_node_put(np); /* Must decrement the refcount */ return 0; } |